© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2295
    Prev
    Next
    INDEX
    Explanations

    say leg

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    丙
    -18.88
    _la
    -18.50
     vec
    -17.75
    vec
    -17.13
     sim
    -16.88
    辛
    -16.75
    乙方
    -16.63
    .vec
    -16.50
    (vec
    -16.13
    -la
    -15.88
    POSITIVE LOGITS
     leg
    46.75
    leg
    46.00
    Leg
    44.75
     Leg
    43.00
    LEG
    39.50
    _leg
    39.25
     len
    38.50
    Lib
    37.75
     legs
    37.75
    -leg
    37.00
    Activations Density 0.171%

    No Known Activations